ReGentS: Real-World Safety-Critical Driving Scenario Generation Made Stable
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910601684451328 |
|---|---|
| author | Yin, Yuan Khayatan, Pegah Zablocki, Éloi Boulch, Alexandre Cord, Matthieu |
| author_facet | Yin, Yuan Khayatan, Pegah Zablocki, Éloi Boulch, Alexandre Cord, Matthieu |
| contents | Machine learning based autonomous driving systems often face challenges with safety-critical scenarios that are rare in real-world data, hindering their large-scale deployment. While increasing real-world training data coverage could address this issue, it is costly and dangerous. This work explores generating safety-critical driving scenarios by modifying complex real-world regular scenarios through trajectory optimization. We propose ReGentS, which stabilizes generated trajectories and introduces heuristics to avoid obvious collisions and optimization problems. Our approach addresses unrealistic diverging trajectories and unavoidable collision scenarios that are not useful for training robust planner. We also extend the scenario generation framework to handle real-world data with up to 32 agents. Additionally, by using a differentiable simulator, our approach simplifies gradient descent-based optimization involving a simulator, paving the way for future advancements. The code is available at https://github.com/valeoai/ReGentS. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_07830 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | ReGentS: Real-World Safety-Critical Driving Scenario Generation Made Stable Yin, Yuan Khayatan, Pegah Zablocki, Éloi Boulch, Alexandre Cord, Matthieu Machine Learning Computer Vision and Pattern Recognition Robotics Machine learning based autonomous driving systems often face challenges with safety-critical scenarios that are rare in real-world data, hindering their large-scale deployment. While increasing real-world training data coverage could address this issue, it is costly and dangerous. This work explores generating safety-critical driving scenarios by modifying complex real-world regular scenarios through trajectory optimization. We propose ReGentS, which stabilizes generated trajectories and introduces heuristics to avoid obvious collisions and optimization problems. Our approach addresses unrealistic diverging trajectories and unavoidable collision scenarios that are not useful for training robust planner. We also extend the scenario generation framework to handle real-world data with up to 32 agents. Additionally, by using a differentiable simulator, our approach simplifies gradient descent-based optimization involving a simulator, paving the way for future advancements. The code is available at https://github.com/valeoai/ReGentS. |
| title | ReGentS: Real-World Safety-Critical Driving Scenario Generation Made Stable |
| topic | Machine Learning Computer Vision and Pattern Recognition Robotics |
| url | https://arxiv.org/abs/2409.07830 |